Research & Data

Claude skill that fetches accurate US stock data via yfinance — works with Claude Code and Claude.ai

Map what the model can see: a no-tool prompt and Codex skill for inspecting an AI agent's current context stack.

A portable agent skill for sharpening research questions.

Codex skill for paper review comments with HTML evidence pages.

Codex skill for adapting and reproducing notebooks in ModelScope Notebook.

Provide open-source Claude Code skills to access HyperX wallet analytics, market data, and social feeds for enhanced trading insights.

Organize real academic research workflows with Claude Code skills for literature tracing, source verification, and bilingual paper search

Claude Code skill + DataForSEO MCP for SEO keyword research — clone and ask your agent to install (see INSTALL.md).

RevOS data-engineering Agent Skills — discoverable via Claude Code plugin marketplace and GitHub-backed skill registries.

Gabriel Murray's personal Claude skills marketplace

自然语言搜索国家税务总局政策法规库 — Hermes Agent Skill

A Codex / Claude skill for recreating UI screenshots as HTML/CSS.

Portable AI skill and Codex-compatible capability pack for traditional Chinese feng shui, wuxing, auspiciousness, spatial analysis, and cross-domain symbolic decision support.

Claude Code skill for searching 51k icons from Iconstack.io — use icons instead of emojis

AI agent skills for strategy discovery with Abel: explore market ideas, analyze causal drivers, and develop investment strategies.

OpenClaw and AI-agent skill for running the Website Email Scraper Apify actor.

Sprint autopilot for BMad Method — drives stories from plan to PR-ready code with git worktrees, commits, and stacked PRs. Plus 7 multi-agent skills: code review, codebase mapping, tech-debt assessment, reverse-architecture, migration planning, research, and multi-persona debate.

Local-first Codex skill and Python CLI for private job-search tracking, semantic reviews, and a static dashboard.

AgentSkill for creating consulting-style HTML presentation decks with static HTML/CSS/JS.

Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.

This is intended as a showcase of my multidisciplinary skills and expertise in robotics, automation, AI/ML, and software. In this project, I leverage AI agents usage and workflows.

Enterprise-grade Codex prompt architect skill with plan-only, approval-gated execution, browser QA, security constraints, and prompt evaluation workflows.

Compare AdaL and Claude Code on Autoresearch benchmarks to find better hyperparameters, run more experiments, and converge faster

Enforce research mode in Claude Code with source citations, direct quotes, and grounded answers to cut hallucinations